AI Platform Reliability & Incident Lead

Legora; Denver (CO); On-site; USD 140,000 - 190,000; Full time

Job summary

Legora in Denver is seeking a senior technical authority to own the most challenging platform escalations in our AI-enabled legal workspace. You will validate platform behavior before release, drive root-cause investigations, and coordinate cross-functional responses with Product Operations and Engineering.

You will serve as the AI subject-matter expert, shaping how the platform handles failures, retrieval quality, and document processing.

Qualifications

• Deep experience in technical support, solutions, or platform-specialist roles with a strong technical bent.
• Strong focus on root cause analysis, logs, data, and systems.

Responsibilities

• Own the hardest problems and drive root cause analysis through logs, data, and system-level checks.
• Validate platform behavior before release; support beta testing and pre-GA investigations and reproduce steps for product teams.
• Detect and declare systemic events, coordinating incident response for Sev1/Sev2 with engineering partners.
• Be the AI subject-matter expert on platform behavior, retrieval quality, and output patterns.
• Advocate for diagnostic tooling and observability improvements in product and engineering reviews.

Skills

AI/LLM systems

Root cause analysis

Escalations handling

Cross-functional communication

Incident response

Observability tooling

Tools

Datadog

Splunk

Jira

Job description

Legora in Denver is seeking a senior technical authority to own the most challenging platform escalations in our AI-enabled legal workspace. You will validate platform behavior before release, drive root-cause investigations, and coordinate cross-functional responses with Product Operations and Engineering.

You will serve as the AI subject-matter expert, shaping how the platform handles failures, retrieval quality, and document processing.